cslt Wiki - 用户贡献 [zh-cn]

2020-10-12

2020-10-11T23:54:29Z

Liuruiqi：

{| class="wikitable"
!People !! This Week !! Next Week !! Task Tracking (DeadLine)
|-

|-
|Dong Wang
||
* Complete the draft for ICASSP factorization paper
* Revise the NL paper
* More refinement for the NN paper
||
* Prepare NSFC defense materials
||
*
|-

|-
|Yunqi Cai
||
*
||
*
||
*
|-

|-
|Zhiyuan Tang
||
*
||
*
||
*
|-

|-
|Lantian Li
||
* Refresh CNC paper (half)
* Release CNC2 data/recipe
* Prepare SD/LT for ICASSP
||
* Complete CNC paper.
||
*
|-

|-
|Ying Shi
||
* Write rebuttal for SLT paper
* DNF based ASR system
||
* test DNF based ASR
||
*
|-

|-
|Haoran Sun
||
* retrain models with phone segments
* experiments in icassp paper
||
* modify icassp paper
* experiments in factorization paper
||
*
|-

|-
|Yue Fan
||
*
||
*
||
*
|-

|-
|Jiawen Kang
||
*
||
*
||
*
|-

|-
|Ruiqi Liu
||
*
||
* Continue to revise the paper
||
*
|-

|-
|Jiao Han
||
*
||
*
||
*
|-

|}

2020-10-05

2020-10-04T23:57:31Z

Liuruiqi：

{| class="wikitable"
!People !! This Week !! Next Week !! Task Tracking (DeadLine)
|-

|-
|Dong Wang
||
* Complete the theory of deep factorization
* Completed the draft for the factorization paper
||
* Lots of paper review
* CN paper revision
||
*
|-

|-
|Yunqi Cai
||
*
||
*
||
*
|-

|-
|Zhiyuan Tang
||
*
||
*
||
*
|-

|-
|Lantian Li
||
* Proposals of SSL and f-DNF
||
* Drafts of CNC and DE-NL.
||
*
|-

|-
|Ying Shi
||
*

||
*
||
*
|-

|-
|Haoran Sun
||
*
||
*
||
*
|-

|-
|Yue Fan
||
*
||
*
||
*
|-

|-
|Jiawen Kang
||
*
||
*
||
*
|-

|-
|Ruiqi Liu
||
* CN2 paper draft
||
*
||
*
|-

|-
|Jiao Han
||
*
||
*
||
*
|-

|}

2020-09-28

2020-09-27T23:43:49Z

Liuruiqi：

{| class="wikitable"
!People !! This Week !! Next Week !! Task Tracking (DeadLine)
|-

|-
|Dong Wang
||
* Formulate the factorization theory
* Factorization paper delayed
||
* Complete the factorization paper
||
*
|-

|-
|Yunqi Cai
||
*
||
*
||
*
|-

|-
|Zhiyuan Tang
||
*
||
*
||
*
|-

|-
|Lantian Li
||
*
||
*
||
*
|-

|-
|Ying Shi
||
*

||
*
||
*
|-

|-
|Haoran Sun
||
* some extra experiments
||
* continue
||
*
|-

|-
|Yue Fan
||
*
||
*
||
*
|-

|-
|Jiawen Kang
||
*
||
*
||
*
|-

|-
|Ruiqi Liu
||
* multi-genre paper experiments
||
* Revise multi-genre paper
||
*
|-

|-
|Jiao Han
||
*
||
*
||
*
|-

|}

2020-09-21

2020-09-20T23:55:23Z

Liuruiqi：

{| class="wikitable"
!People !! This Week !! Next Week !! Task Tracking (DeadLine)
|-

|-
|Dong Wang
||
* Finish the first draft for the factorization paper
||
* Refine the multi-genre paper and factorization paper
||
*
|-

|-
|Yunqi Cai
||
* review papers and experiments on PCA-flow
||
*
||
*
|-

|-
|Zhiyuan Tang
||
*
||
*
||
*
|-

|-
|Lantian Li
||
* Clear up multi-genre exps.
* Prepare data/exp for Huawei project report.
* Build our annual delivery.
||
* Go on DE-NL and CPC.
||
*
|-

|-
|Ying Shi
||
* read paper about score matching
* prepare report about score matching
* some course
||
* make a presentation about score matching
||
*
|-

|-
|Haoran Sun
||
* some experiments related to factorization
||
* continue
||
*
|-

|-
|Yue Fan
||
*
||
*
||
*
|-

|-
|Jiawen Kang
||
*
||
*
||
*
|-

|-
|Ruiqi Liu
||
* Revise multi-genre paper
||
* Revise multi-genre paper
* 16k ASR lm self-adaptation tools
||
*
|-

|-
|Jiao Han
||
*
||
*
||
*
|-

|}

2020-09-21

2020-09-20T23:54:22Z

Liuruiqi：

{| class="wikitable"
!People !! This Week !! Next Week !! Task Tracking (DeadLine)
|-

|-
|Dong Wang
||
* Finish the first draft for the factorization paper
||
* Refine the multi-genre paper and factorization paper
||
*
|-

|-
|Yunqi Cai
||
* review papers and experiments on PCA-flow
||
*
||
*
|-

|-
|Zhiyuan Tang
||
*
||
*
||
*
|-

|-
|Lantian Li
||
* Clear up multi-genre exps.
* Prepare data/exp for Huawei project report.
* Build our annual delivery.
||
* Go on DE-NL and CPC.
||
*
|-

|-
|Ying Shi
||
*

||
*
||
*
|-

|-
|Haoran Sun
||
* some experiments related to factorization
||
* continue
||
*
|-

|-
|Yue Fan
||
*
||
*
||
*
|-

|-
|Jiawen Kang
||
*
||
*
||
*
|-

|-
|Ruiqi Liu
||
*
||
* Revise multi-genre paper
* 16k ASR lm self-adaptation tools
||
*
|-

|-
|Jiao Han
||
*
||
*
||
*
|-

|}

2020-09-14

2020-09-13T23:53:44Z

Liuruiqi：

{| class="wikitable"
!People !! This Week !! Next Week !! Task Tracking (DeadLine)
|-

|-
|Dong Wang
||
* Revising factorization paper
* More study on the foundation of visual-audio SRE by neural Bayes.
||
* Complete the revision for the factorization paper
||
*
|-

|-
|Yunqi Cai
||
* Review papers of deep Generative model and multiscale learning
||
*
||
*
|-

|-
|Zhiyuan Tang
||
* Some survey on new model/struct for G&D.
||
* Try some new.
||
*
|-

|-
|Lantian Li
||
*
||
*
||
*
|-

|-
|Ying Shi
||
*

||
*
||
*
|-

|-
|Haoran Sun
||
* modified the speech factorization paper
||
* continue modification
* investigation on independence between phones and speakers
||
*
|-

|-
|Yue Fan
||
*
||
*
||
*
|-

|-
|Jiawen Kang
||
*
||
*
||
*
|-

|-
|Ruiqi Liu
||
* Add some experiments
* Modify the paper
||
* Continue modify the paper
||
*
|-

|-
|Haolin Chen
||
*
||
*
||
*
|-

|-
|Jiao Han
||
*
||
*
||
*
|-

|}

2020-09-07

2020-09-06T23:37:33Z

Liuruiqi：

{| class="wikitable"
!People !! This Week !! Next Week !! Task Tracking (DeadLine)
|-

|-
|Dong Wang
||
*
||
*
||
*
|-

|-
|Yunqi Cai
||
*
||
*
||
*
|-

|-
|Zhiyuan Tang
||
*
||
*
||
*
|-

|-
|Lantian Li
||
* Summarize uncertainty modeling on ASV.
* Submit ETM paper.
||
* Go on decoupled NL.
||
*
|-

|-
|Ying Shi
||
*

||
*
||
*
|-

|-
|Haoran Sun
||
* Some extra experiments
||
* Modify the speech factorization paper
||
*
|-

|-
|Yue Fan
||
*
||
*
||
*
|-

|-
|Jiawen Kang
||
* Learn uncertainty modeling;
* Check ETM paper.
||
* Multi-condition paper;
* Continue uncertainty modeling.
||
*
|-

|-
|Ruiqi Liu
||
*
||
* Supplement multi-condition paper.
||
*
|-

|-
|Haolin Chen
||
*
||
*
||
*
|-

|-
|Jiao Han
||
*
||
*
||
*
|-

|}

2020-08-24

2020-08-23T23:39:55Z

Liuruiqi：

{| class="wikitable"
!People !! This Week !! Next Week !! Task Tracking (DeadLine)
|-

|-
|Dong Wang
||
* Solid the foundation of dePLDA
* More reference on cnmatch scoring
* Start working on CNCeleb2 paper
||
* Complete the CNCeleb2 paper
||
*
|-

|-
|Yunqi Cai
||
*
||
*
||
*
|-

|-
|Zhiyuan Tang
||
*
||
*
||
*
|-

|-
|Lantian Li
||
*
||
*
||
*
|-

|-
|Ying Shi
||
*

||
*
||
*
|-

|-
|Haoran Sun
||
*
||
*
||
*
|-

|-
|Yue Fan
||
*
||
*
||
*
|-

|-
|Jiawen Kang
||
*
*
||
*
*
||
*
|-

|-
|Ruiqi Liu
||
* CNCeleb2 paper draft.
||
* Continue to revise the paper.
||
*
|-

|-
|Haolin Chen
||
*
||
*
||
*
|-

|}

2020-08-17

2020-08-16T23:53:07Z

Liuruiqi：

{| class="wikitable"
!People !! This Week !! Next Week !! Task Tracking (DeadLine)
|-

|-
|Dong Wang
||
* First round of check for the statstics decomposition (SD) paper.
* Theory foundation for decoupled scoring.
||
* Further invetigation for the decoupled scoring
||
*
|-

|-
|Yunqi Cai
||
*MG training on Anormaly detection task
||
*
||
*
|-

|-
|Zhiyuan Tang
||
*
||
*
||
*
|-

|-
|Lantian Li
||
*
||
*
||
*
|-

|-
|Ying Shi
||
*

||
*
||
*
|-

|-
|Haoran Sun
||
* Speech factorization paper
||
* Finish this paper
||
*
|-

|-
|Yue Fan
||
*
||
*
||
*
|-

|-
|Jiawen Kang
||
*
*
||
*
*
||
*
|-

|-
|Ruiqi Liu
||
*Revise the paper.
*Investigate SRE dataset.
||
*Charts and tables in papers.
*Continue to revise the paper
||
*
|-

|-
|Haolin Chen
||
*
||
*
||
*
|-

|}

2020-08-17

2020-08-16T23:52:35Z

Liuruiqi：

{| class="wikitable"
!People !! This Week !! Next Week !! Task Tracking (DeadLine)
|-

|-
|Dong Wang
||
* First round of check for the statstics decomposition (SD) paper.
* Theory foundation for decoupled scoring.
||
* Further invetigation for the decoupled scoring
||
*
|-

|-
|Yunqi Cai
||
*MG training on Anormaly detection task
||
*
||
*
|-

|-
|Zhiyuan Tang
||
*
||
*
||
*
|-

|-
|Lantian Li
||
*
||
*
||
*
|-

|-
|Ying Shi
||
*

||
*
||
*
|-

|-
|Haoran Sun
||
* Speech factorization paper
||
* Finish this paper
||
*
|-

|-
|Yue Fan
||
*
||
*
||
*
|-

|-
|Jiawen Kang
||
*
*
||
*
*
||
*
|-

|-
|Ruiqi Liu
||
*revise the paper.
*investigate SRE dataset.
||
*Charts and tables in papers.
*Continue to revise the paper
||
*
|-

|-
|Haolin Chen
||
*
||
*
||
*
|-

|}

2020-08-10

2020-08-09T23:44:45Z

Liuruiqi：

{| class="wikitable"
!People !! This Week !! Next Week !! Task Tracking (DeadLine)
|-

|-
|Dong Wang
||
*
||
*
||
*
|-

|-
|Yunqi Cai
||
*More investigation on MG training
*MG investigation on image data set
||
*
||
*
|-

|-
|Zhiyuan Tang
||
*
||
*
||
*
|-

|-
|Lantian Li
||
*
||
*
||
*
|-

|-
|Ying Shi
||
*

||
*
||
*
|-

|-
|Haoran Sun
||
*
||
*
||
*
|-

|-
|Yue Fan
||
*
||
*
||
*
|-

|-
|Jiawen Kang
||
*
*
||
*
*
||
*
|-

|-
|Ruiqi Liu
||
*Finish the maml experiments
||
*Continue to revise the paper
||
*
|-

|-
|Haolin Chen
||
* finish ml denoising exp, paper
||
*
||
*
|-

|}

2020-08-03

2020-08-02T23:58:34Z

Liuruiqi：

{| class="wikitable"
!People !! This Week !! Next Week !! Task Tracking (DeadLine)
|-

|-
|Dong Wang
||
*
||
*
||
*
|-

|-
|Yunqi Cai
||
*
||
*
||
*
|-

|-
|Zhiyuan Tang
||
*
||
*
||
*
|-

|-
|Lantian Li
||
* Enroll-test mismatch (reproduce exps and write paper).
||
* Complete ETM paper.
||
*
|-

|-
|Ying Shi
||
* write paper for APSIPA 2020
||
* finish the paper
||
*
|-

|-
|Haoran Sun
||
*
||
*
||
*
|-

|-
|Yue Fan
||
*
||
*
||
*
|-

|-
|Jiawen Kang
||
*
*
||
*
*
||
*
|-

|-
|Ruiqi Liu
||
* MC experiments
* maml multi-genre generalization.
||
*finish the experiments
||
*
|-

|-
|Haolin Chen
||
*
||
*
||
*
|-

|}

2020-08-03

2020-08-02T23:57:59Z

Liuruiqi：

{| class="wikitable"
!People !! This Week !! Next Week !! Task Tracking (DeadLine)
|-

|-
|Dong Wang
||
*
||
*
||
*
|-

|-
|Yunqi Cai
||
*
||
*
||
*
|-

|-
|Zhiyuan Tang
||
*
||
*
||
*
|-

|-
|Lantian Li
||
* Enroll-test mismatch (reproduce exps and write paper).
||
* Complete ETM paper.
||
*
|-

|-
|Ying Shi
||
* write paper for APSIPA 2020
||
* finish the paper
||
*
|-

|-
|Haoran Sun
||
*
||
*
||
*
|-

|-
|Yue Fan
||
*
||
*
||
*
|-

|-
|Jiawen Kang
||
*
*
||
*
*
||
*
|-

|-
|Ruiqi Liu
||
* MC experiments
* maml multi-genre generalization.
||
*
||
*
|-

|-
|Haolin Chen
||
*
||
*
||
*
|-

|}

2020-07-27

2020-07-26T22:55:22Z

Liuruiqi：

{| class="wikitable"
!People !! This Week !! Next Week !! Task Tracking (DeadLine)
|-

|-
|Dong Wang
||
*
||
*
||
*
|-

|-
|Yunqi Cai
||
*
||
*
||
*
|-

|-
|Zhiyuan Tang
||
*
||
*
||
*
|-

|-
|Lantian Li
||
*
||
*
||
*
|-

|-
|Ying Shi
||
*

||
*
||
*
|-

|-
|Haoran Sun
||
* Analysed latent space of ML-DNF
* Classification via logpz
||
* Analysises of subspace DNF
||
*
|-

|-
|Yue Fan
||
*
||
*
||
*
|-

|-
|Jiawen Kang
||
* Read NDA papers;
* MAML code;
* MAML experiments.
||
* MAML SSMC&MC experiments.
||
*
|-

|-
|Ruiqi Liu
||
* revise the paper draft.
* Multi-genre generalization.
* MC experiments data.
||
* MC experiments
||
*
|-

|-
|Haolin Chen
||
*
||
*
||
*
|-

|}

文件:Multi-condition.rar

2020-07-24T02:15:33Z

Liuruiqi：Multi-condition paper draft

Multi-condition paper draft

2020-07-20

2020-07-19T23:59:22Z

Liuruiqi：

{| class="wikitable"
!People !! This Week !! Next Week !! Task Tracking (DeadLine)
|-

|-
|Dong Wang
||
* Explore the theoreteical explanation of the regularied training
* More work on the NB theory.
||
* Complete Yunqi's TASLP paper.
||
*
|-

|-
|Yunqi Cai
||
*
||
*
||
*
|-

|-
|Zhiyuan Tang
||
* Adaptation for dt-dnf asr.
||
* Continue.
||
*
|-

|-
|Lantian Li
||
* Enroll-test mismatch (MCT vs. MLE, MLE-p vs. MLE-f)
||
* Complete enroll-test's paper.
||
*
|-

|-
|Ying Shi
||
* investigate about how to augment data with sub space flow
* train a new sub space flow with learnable mean
||
* test a new sub space flow with learnable mean
||
*
|-

|-
|Haoran Sun
||
* some analysises of latent space on VAE, RealNVP and DNF
||
* more analysises on DNF
||
*
|-

|-
|Yue Fan
||
*
||
*
||
*
|-

|-
|Jiawen Kang
||
* RobustMAML experiments
* Revise Paper
* Mismatch experiments
||
* RobustMAML experiments
* Mismatch experiments
||
*
|-

|-
|Ruiqi Liu
||
* Continue to revise the paper
* MCT and MAML experiments
||
* Continue these work
||
*
|-

|-
|Haolin Chen
||
* Analysis on subspace Flow r space
||
* Subspace Flow
||
*
|-

|}

2020-07-13

2020-07-12T23:16:32Z

Liuruiqi：

{| class="wikitable"
!People !! This Week !! Next Week !! Task Tracking (DeadLine)
|-

|-
|Dong Wang
||
* deepnorm2 paper refinement.
* More investigation on the optimum with NL, e.g., the global thresholding property
* Formulation for AV denosing and phone-aware DNF/NDA
* Continue the NB book.
||
* Complete the formulation of the AV denoising approach.
* Continue the NB book
||
*
|-

|-
|Yunqi Cai
||
*
||
*
||
*
|-

|-
|Zhiyuan Tang
||
*
||
*
||
*
|-

|-
|Lantian Li
||
*
||
*
||
*
|-

|-
|Ying Shi
||
* BP + length norm enhancement method
* Sub-space flow
||
* Continue on Sub-space flow
** Multi-SNR variance
** Cyclic loss
* Sub-space plan B
||
*
|-

|-
|Haoran Sun
||
* Analyzed latent space of VAE and AE on TIMIT
||
* The same analysis on VAE with larger latent space dimension
* The same analysis on Glow
* Supervised approaches
||
*
|-

|-
|Yue Fan
||
*
||
*
||
*
|-

|-
|Jiawen Kang
||
* Prepare new Near-far data
* Collect experiments data
* Write multi-conditon paper
||
* Revise multi-conditon paper
* MAML experiments
||
*
|-

|-
|Ruiqi Liu
||
*Complete the experiment and write the paper.
||
*Continue.
||
*
|-

|-
|Haolin Chen
||
*
||
*
||
*
|-

|}

2020-07-06

2020-07-05T23:58:37Z

Liuruiqi：

{| class="wikitable"
!People !! This Week !! Next Week !! Task Tracking (DeadLine)
|-

|-
|Dong Wang
||
* More deisgn on prior-based denoising
* Investigation on the optimum of NL with respect to liklihood ratio test
||
* Complete the deepnorm2 paper
* Continue on the neural Bayes book
||
*
|-

|-
|Yunqi Cai
||
*
||
*
||
*
|-

|-
|Zhiyuan Tang
||
* BetaFlow.
* Layer-by-layer training for flow.
* Det-constant flow.
||
* Analyse det-constant (mostly 1) flow.
||
*
|-

|-
|Lantian Li
||
*
||
*
||
*
|-

|-
|Ying Shi
||
*

||
*
||
*
|-

|-
|Haoran Sun
||
*
||
*
||
*
|-

|-
|Yue Fan
||
*
||
*
||
*
|-

|-
|Jiawen Kang
||
* Write multi-condition paper.
* Arrange near-far data.
||
* Arrange cross-channel data.
* Modify code for new data.
||
*
|-

|-
|Ruiqi Liu
||
* Paper draft
||
* Complete the experiment and modify the paper
||
*
|-

|-
|Haolin Chen
||
* FFJORD/Glow test on BP denoising
* Review papers on self-supervised learning in speech processing
* Prepare for the report
||
* Subspace method for denoising
||
*
|-

|}

2020-06-29

2020-06-29T00:02:29Z

Liuruiqi：

{| class="wikitable"
!People !! This Week !! Next Week !! Task Tracking (DeadLine)
|-

|-
|Dong Wang
||
* Deepnorm2 paper darft finished
||
* Deepnorm2 paper polishing
||
*
|-

|-
|Yunqi Cai
||
*
||
*
||
*
|-

|-
|Zhiyuan Tang
||
* Test FFJORD.
||
* Back to AEFlow.
||
*
|-

|-
|Lantian Li
||
*
||
*
||
*
|-

|-
|Ying Shi
||
* Gradient based speech enhancement method with Gauss. length norm(x space)
* Gradient based speech enhancement method with Gauss. length norm(z space)
||
*
||
*
|-

|-
|Haoran Sun
||
*
||
*
||
*
|-

|-
|Yue Fan
||
*Reproduce the baseline based on MFCC-GMM.
||
*Control Variable Experiment
||
*
|-

|-
|Jiawen Kang
||
*
||
*
||
*
|-

|-
|Ruiqi Liu
||
* More investigates and experments on i-vector anfd x-vector recipe use CN2 data .
||
* Further analysis on CN dataset several notable factors, including genres, duration, gender, age ..
||
*
|-

|-
|Sitong Cheng
||
*
||
*
||
*
|-

|-
|Zhixin Liu
||
*
||
*
||
*
|-

|-
|Haolin Chen
||
* FFJORD hands on and test
* Reviewed papers on unsupervised denoising
||
* Investigate other methods
||
*
|-

|}

2020-06-22

2020-06-21T23:20:56Z

Liuruiqi：

{| class="wikitable"
!People !! This Week !! Next Week !! Task Tracking (DeadLine)
|-

|-
|Dong Wang
||
* More investigation on VAE OT
* Investigation on ODE CNF
||
* Subspace DNF paper
||
*
|-

|-
|Yunqi Cai
||
*
||
*
||
*
|-

|-
|Zhiyuan Tang
||
*
||
*
||
*
|-

|-
|Lantian Li
||
* Polish our TASLP paper.
* Enroll-test mismatch.
||
* AE Flow.
||
*
|-

|-
|Ying Shi
||
*
||
*
||
*
|-

|-
|Haoran Sun
||
*
||
*
||
*
|-

|-
|Yue Fan
||
*
||
*
||
*
|-

|-
|Jiawen Kang
||
*
||
*
||
*
|-

|-
|Ruiqi Liu
||
* More analysis and experiments about CN2.
||
* Continue to complete the experiments according to the experiment plan.
||
*
|-

|-
|Sitong Cheng
||
*
||
*
||
*
|-

|-
|Zhixin Liu
||
*
||
*
||
*
|-

|-
|Haolin Chen
||
* AE Training
* VAE-NMF hands on
* Review papers on Unsupervised SE, OT, Neural ODE
||
* Exploration on our method
||
*
|-

|}

2020-06-15

2020-06-14T23:55:09Z

Liuruiqi：

{| class="wikitable"
!People !! This Week !! Next Week !! Task Tracking (DeadLine)
|-

|-
|Dong Wang
||
*
||
*
||
*
|-

|-
|Yunqi Cai
||
*
||
*
||
*
|-

|-
|Zhiyuan Tang
||
*
||
*
||
*
|-

|-
|Lantian Li
||
* i-vector, DNF, NDA, CNDA, NJFA.
* Enroll-test mismatch.
||
* Polish our TASLP paper.
||
*
|-

|-
|Ying Shi
||
* GAN source separation
* GAN method on flow
||
* GAN-OMT
* review more paper about speech enhancement
||
*
|-

|-
|Haoran Sun
||
*
||
*
||
*
|-

|-
|Yue Fan
||
*Experimental program
*Experiment on svm
||
*Experiment on different models
||
*
|-

|-
|Jiawen Kang
||
*
||
*
||
*
|-

|-
|Ruiqi Liu
||
* Experiments on cnceleb2.
||
* Continue
||
*
|-

|-
|Sitong Cheng
||
*
||
*
||
*
|-

|-
|Zhixin Liu
||
*
||
*
||
*
|-

|-
|Haolin Chen
||
*
||
* Back to work.
||
*
|-

|}

2020-06-08

2020-06-07T23:48:42Z

Liuruiqi：

{| class="wikitable"
!People !! This Week !! Next Week !! Task Tracking (DeadLine)
|-

|-
|Dong Wang
||
* Complete reviwing ICASSP 20 papers reltaed to speker recognition
* Sick leave
||
*
||
*
|-

|-
|Yunqi Cai
||
*
||
*
||
*
|-

|-
|Zhiyuan Tang
||
*
||
*
||
*
|-

|-
|Lantian Li
||
*
||
*
||
*
|-

|-
|Ying Shi
||
* M2ASR data
* NMF baseline
* VAE-NMF baseline
||
* Our method on GAN
* Energy model
||
*
|-

|-
|Haoran Sun
||
*
||
*
||
*
|-

|-
|Yue Fan
||
*
||
*
||
*
|-

|-
|Jiawen Kang
||
*
||
*
||
*
|-

|-
|Ruiqi Liu
||
* Kaldi cnceleb2 experiments.
||
* Kaldi cnceleb2 experiments.
* SOTA model experiments on CN-Celeb2.
||
*
|-

|-
|Sitong Cheng
||
*
||
*
||
*
|-

|-
|Zhixin Liu
||
*
||
*
||
*
|-

|-
|Haolin Chen
||
*
||
*
||
*
|-

|}

2020-06-01

2020-05-31T23:56:44Z

Liuruiqi：

{| class="wikitable"
!People !! This Week !! Next Week !! Task Tracking (DeadLine)
|-

|-
|Dong Wang
||
* Completed the review of the semi-supervised speech enhancement approach
* Review ICASSP 2020 papers related to speaker recognition
||
* Continue review on ICASSP 2020
* More investigation on the generalization problem of deep generative models.
||
*
|-

|-
|Yunqi Cai
||
*
||
*
||
*
|-

|-
|Zhiyuan Tang
||
* DNF/DT on ASR.
||
* Continues.
||
*
|-

|-
|Lantian Li
||
*
||
*
||
*
|-

|-
|Ying Shi
||
* finish new flow with both postive samples and negative samples
* finish RPCA baseline
* finish energy model
||
* M2ASR data
* NMF baseline
* finish VAE-NMF baseline
* review more paper about speech enhancement
||
*
|-

|-
|Haoran Sun
||
*
||
*
||
*
|-

|-
|Yue Fan
||
*Experiments on mdl-cnc based gun vector
||
*Train the acoustic space with existing audioset data
*Review of Acoustic Scene Classification
||
*
|-

|-
|Jiawen Kang
||
*
||
*
||
*
|-

|-
|Ruiqi Liu
||
* Make CN-Celeb2 data
* Kaldi cnceleb2 experiment
||
* Kaldi cnceleb2 experiment
* SOTA model on CN-Celeb2
||
*
|-

|-
|Sitong Cheng
||
*
||
*
||
*
|-

|-
|Zhixin Liu
||
*
||
*
||
*
|-

|-
|Haolin Chen
||
*
||
*
||
*
|-

|}

2020-05-25

2020-05-24T22:35:59Z

Liuruiqi：

{| class="wikitable"
!People !! This Week !! Next Week !! Task Tracking (DeadLine)
|-

|-
|Dong Wang
||
*
||
*
||
*
|-

|-
|Yunqi Cai
||
*
||
*
||
*
|-

|-
|Zhiyuan Tang
||
*
||
*
||
*
|-

|-
|Lantian Li
||
*
||
*
||
*
|-

|-
|Ying Shi
||
*
||
*
||
*
|-

|-
|Haoran Sun
||
*
||
*
||
*
|-

|-
|Yue Fan
||
*
||
*
||
*
|-

|-
|Jiawen Kang
||
* Organize meta-learning code
* Check cn2
* Prepare shared PPT
||
* Prepare cross-channel and near-far data.
||
*
|-

|-
|Ruiqi Liu
||
*
||
* Kaldi baseline experiments on cn2.
* Get some information about speakers to analyze cn2.
* Other experiments.
||
*
|-

|-
|Sitong Cheng
||
*
||
*
||
*
|-

|-
|Zhixin Liu
||
*
||
*
||
*
|-

|-
|Haolin Chen
||
*
||
*
||
*
|-

|}

2020-05-18

2020-05-18T02:33:38Z

Liuruiqi：

{| class="wikitable"
!People !! This Week !! Next Week !! Task Tracking (DeadLine)
|-

|-
|Dong Wang
||
*
||
*
||
*
|-

|-
|Yunqi Cai
||
*
||
*
||
*
|-

|-
|Zhiyuan Tang
||
*
||
*
||
*
|-

|-
|Lantian Li
||
*
||
*
||
*
|-

|-
|Ying Shi
||
* norm flow model with raw signal feature
* 4 prior enhancement methods on raw signal feature
* investigate about why 0 tensor always get higher likelihood score
||
* continue investigate prior methods
||
*
|-

|-
|Haoran Sun
||
*
||
*
||
*
|-

|-
|Yue Fan
||
*
||
*
||
*
|-

|-
|Jiawen Kang
||
* Finish interspeech paper.
||
* Make cnceleb2.
* Prepare the next task.
||
*
|-

|-
|Ruiqi Liu
||
* Interspeech paper.
||
* Solve some ASR Model problems raised by Hualai and Shengyuan companies last week.
* .
||
*
|-

|-
|Sitong Cheng
||
*
||
*
||
*
|-

|-
|Zhixin Liu
||
*
||
*
||
*
|-

|-
|Haolin Chen
||
*
||
*
||
*
|-

|}

2020-05-11

2020-05-10T23:45:11Z

Liuruiqi：

{| class="wikitable"
!People !! This Week !! Next Week !! Task Tracking (DeadLine)
|-

|-
|Dong Wang
||
*
||
*
||
*
|-

|-
|Yunqi Cai
||
* check book
* some experiments on DNF2
||
*
||
*
|-

|-
|Zhiyuan Tang
||
*
||
*
||
*
|-

|-
|Lantian Li
||
* More study on LDA, PLDA and NDA.
* INTERSPEECH paper.
||
* INTERSPEECH paper.
||
*
|-

|-
|Ying Shi
||
*
||
*
||
*
|-

|-
|Haoran Sun
||
*
||
*
||
*
|-

|-
|Yue Fan
||
* Summarization of data information
* presentation of icassp
* Redownloaded the gunshot data on youtube
||
* Prepare the data needed for the new experiments
||
*
|-

|-
|Jiawen Kang
||
*
||
*
||
*
|-

|-
|Ruiqi Liu
||
* Organize all the results and prepare the paper.
||
* Continue to prepare the paper.
||
*
|-

|-
|Sitong Cheng
||
*
||
*
||
*
|-

|-
|Zhixin Liu
||
*
||
*
||
*
|-

|-
|Haolin Chen
||
*
||
*
||
*
|-

|}

2020-05-04

2020-05-06T00:02:51Z

Liuruiqi：

{| class="wikitable"
!People !! This Week !! Next Week !! Task Tracking (DeadLine)
|-

|-
|Dong Wang
||
*
||
*
||
*
|-

|-
|Yunqi Cai
||
*
||
*
||
*
|-

|-
|Zhiyuan Tang
||
* Check speec book.
* Autoreg flow.
||
* Autoreg flow.
* GOP score.
||
*
|-

|-
|Lantian Li
||
* Write SRE chapter of Speech book.
* Write 'Shui Mu' application.
||
* Write INTERSPEECH paper.
||
*
|-

|-
|Ying Shi
||
* Write and check speech book
* Speech enhancement experiments based on clean&noise flow prior
||
* INTERSPEECH paper (RPCA, DNN_IRM, flow prior method)
||
*
|-

|-
|Haoran Sun
||
*
||
*
||
*
|-

|-
|Yue Fan
||
*
||
*
||
*
|-

|-
|Jiawen Kang
||
* Meta learning EER curve.
||
* Prepare for Interspeech.
||
*
|-

|-
|Ruiqi Liu
||
* Multi-scene generalization via meta-learning.
||
* Organize all the results and prepare the paper.
||
*
|-

|-
|Sitong Cheng
||
*
||
*
||
*
|-

|-
|Zhixin Liu
||
*
||
*
||
*
|-

|-
|Haolin Chen
||
*
||
*
||
*
|-

|}

2020-04-27

2020-04-27T00:24:19Z

Liuruiqi：

{| class="wikitable"
!People !! This Week !! Next Week !! Task Tracking (DeadLine)
|-

|-
|Dong Wang
||
* Speech Book two chapters completed
||
* Check speech book
||
*
|-

|-
|Yunqi Cai
||
* check speach book
||
*
*
||
*
|-

|-
|Zhiyuan Tang
||
* Speech book revise.
* Autoregressive glow.
||
* Deliver speech book.
||
*
|-

|-
|Lantian Li
||
* Solve the mismatch between NL scoring and PLDA scoring.
* Study the relationship between NDA and PLDA.
* Study the length normalization before NL/PLDA scoring
* Check speech book
||
* Check speech book
||
*
|-

|-
|Ying Shi
||
* Experiments about condition + prior methods for speech enhancement
* Experiments about self supervised enhancement method
||
* Check book and finish it
* self supervised enhancement method
||
*
|-

|-
|Haoran Sun
||
*
||
*
||
*
|-

|-
|Yue Fan
||
* Get 1000-people data
||
*Complete the data collection of cn-celeb2
*Continue the experiments of gun detection
||
*
|-

|-
|Jiawen Kang
||
* Finish experiments about deeper net.
* Repeat experiments on singing, moive, play.
||
* Write experiments report.
||
*
|-

|-
|Ruiqi Liu
||
* Multi-Scene Generalization test via meta-learning.
||
* Organize all the results and make an experiment report.
||
*
|-
S

|-
|Sitong Cheng
||
*
||
*
||
*
|-

|-
|Zhixin Liu
||
*
||
*
||
*
|-

|-
|Haolin Chen
||
* Rerun experiments on double flow structures with white noise
* Test models on white noise
||
* Rerun experiments on double flow structures with other enrionmental noise
* Semi-supervised training with double flow
||
*
|-

|}

2020-04-27

2020-04-27T00:04:36Z

Liuruiqi：

{| class="wikitable"
!People !! This Week !! Next Week !! Task Tracking (DeadLine)
|-

|-
|Dong Wang
||
* Speech Book two chapters completed
||
* Check speech book
||
*
|-

|-
|Yunqi Cai
||
* check speach book
||
*
*
||
*
|-

|-
|Zhiyuan Tang
||
*
*
||
*
||
*
|-

|-
|Lantian Li
||
*
*
||
*
||
*
|-

|-
|Ying Shi
||
* Experiments about condition + prior methods for speech enhancement
* Experiments about self supervised enhancement method
||
* Check book and finish it
* self supervised enhancement method
||
*
|-

|-
|Haoran Sun
||
*
||
*
||
*
|-

|-
|Yue Fan
||
* Get 1000-people data
||
*Complete the data collection of cn-celeb2
*Continue the experiments of gun detection
||
*
|-

|-
|Jiawen Kang
||
*
||
*
||
*
|-

|-
|Ruiqi Liu
||
* Multi-scene domain Generalization test via meta-learning.
||
* Organize all the results and make an experiment report.
||
*
|-

|-
|Sitong Cheng
||
*
||
*
||
*
|-

|-
|Zhixin Liu
||
*
||
*
||
*
|-

|-
|Haolin Chen
||
* Rerun experiments on double flow structures with white noise
* Test models on white noise
||
* Rerun experiments on double flow structures with other enrionmental noise
* Semi-supervised training with double flow
||
*
|-

|}

2020-04-20

2020-04-19T23:50:40Z

Liuruiqi：

{| class="wikitable"
!People !! This Week !! Next Week !! Task Tracking (DeadLine)
|-

|-
|Dong Wang
||
* Book chapter for language recognition and emotion recognition
* Design prior + condition approach for speech enhancement
||
* Complete the two chapters of the speech book

||
*
|-

|-
|Yunqi Cai
||
* some simulate experiments on VAE-NDA model
* check ASR book
||
*
*
||
*
|-

|-
|Zhiyuan Tang
||
*
*
||
*
||
*
|-

|-
|Lantian Li
||
*
*
||
*
||
*
|-

|-
|Ying Shi
||
* Write speech book of minority chapter
* Summary experiment about speech enhancement
||
* Finish speech book
* Make report about speech enhancement
||
*
|-

|-
|Haoran Sun
||
*
||
*
||
*
|-

|-
|Yue Fan
||
* Download all the data of cn2
* Processed 90% of data
* Make poster and video of Icassp
||
* Get 1000-people data
||
*
|-

|-
|Jiawen Kang
||
*
||
*
||
*
|-

|-
|Ruiqi Liu
||
* Meta-learning experiments.
* ASR engine authorization for Shengyuan company.
||
* Continue last week's work.
||
*
|-

|-
|Sitong Cheng
||
*
||
*
||
*
|-

|-
|Zhixin Liu
||
*
||
*
||
*
|-

|-
|Haolin Chen
||
* Experiments on BP denoising
||
* Finalize all results
||
*
|-

|}

2020-04-13

2020-04-13T00:02:56Z

Liuruiqi：

{| class="wikitable"
!People !! This Week !! Next Week !! Task Tracking (DeadLine)
|-

|-
|Dong Wang
||
*
*
*
||
*
*
||
*
|-

|-
|Yunqi Cai
||
*
*
*
||
*
*
||
*
|-

|-
|Zhiyuan Tang
||
* Basic glow as pretraining for nda, not work now.
* NDA +Discriminative training, not work now.
||
* Analyse the trained models.
||
*
|-

|-
|Lantian Li
||
*
*
||
*
||
*
|-

|-
|Ying Shi
||
*
*
||
*
*
||
*
|-

|-
|Haoran Sun
||
*
||
*
||
*
|-

|-
|Yue Fan
||
*
*
||
*
||
*
|-

|-
|Jiawen Kang
||
*
||
*
||
*
|-

|-
|Ruiqi Liu
||
* meta-learning experiments with Jiawen.
* ASR model training for Shengyuan company.
||
* Continue last week's work.
||
*
|-

|-
|Sitong Cheng
||
*
||
*
||
*
|-

|-
|Zhixin Liu
||
*
||
*
||
*
|-

|-
|Haolin Chen
||
* Investigation on noise to clean latent space mapping
||
* Cooperate with Shi Ying
||
*
|-

|}

2020-04-06

2020-04-06T23:58:35Z

Liuruiqi：

{| class="wikitable"
!People !! This Week !! Next Week !! Task Tracking (DeadLine)
|-

|-
|Dong Wang
||
* More work on NPCA. Experiments show it works, but I still cannot find a reasonable probabilsitic framework to explain the results
* Some work on NF-based on MNIST generation, with MSE loss. No good performance is obtained right now.
||
* More investigation on NPCA. If cannot get result, skip it right now.
* Investigation on conditional NDA.
* Investigation on approximation power of NF.
||
*
|-

|-
|Yunqi Cai
||
*
*
*
||
*
*
||
*
|-

|-
|Zhiyuan Tang
||
* Phone-ali conditioned NDA. Struct not work yet.
||
* Continue.
||
*
|-

|-
|Lantian Li
||
* Overview Bayesian scoring methods.
* Obtain a basic result of NDA scoring on x/i-vector.
||
* Go on study NDA scoring.
||
*
|-

|-
|Ying Shi
||
*
*
||
*
*
||
*
|-

|-
|Haoran Sun
||
*
||
*
||
*
|-

|-
|Yue Fan
||
* Work on the arrangements of cn2
* Experimented with gun and nongun on dnf
||
*Do more experiments on dnf for classification
||
*
|-

|-
|Jiawen Kang
||
*
||
*
||
*
|-

|-
|Ruiqi Liu
||
* Study meta-learning experiments and get the EER in different domains.
* Arrange ASR training tools.
||
* Continue meta-learning experiments.
||
*
|-

|-
|Sitong Cheng
||
*
||
*
||
*
|-

|-
|Zhixin Liu
||
*
||
*
||
*
|-

|-
|Haolin Chen
||
* Some investigations on sequential flow
||
* Cooperate with Shi Ying on experiments
||
*
|-

|}

2020-03-30

2020-03-29T23:17:28Z

Liuruiqi：

{| class="wikitable"
!People !! This Week !! Next Week !! Task Tracking (DeadLine)
|-

|-
|Dong Wang
||
* Establish neural Bayes theory
* Unify the subspace DNF and NDA
* More investigation on neural PCA
||
* More work on neural PCA
* Investigate incremental training algorithm
||
*
|-

|-
|Yunqi Cai
||
* Did some experiments on VAE Bayes score
* Apply NDA to xvector's deep normlization
* Investigate the literature on Deep generative model
||
* keep on literature Investigation
* Give some consistent reults on NDA-xvector deep normlization
||
*
|-

|-
|Zhiyuan Tang
||
*
||
*
||
*
|-

|-
|Lantian Li
||
*
||
*
||
*
|-

|-
|Ying Shi
||
*
||
*
||
*
|-

|-
|Wenqiang Du
||
*
||
*
||
*
|-

|-
|Haoran Sun
||
*
||
*
||
*
|-

|-
|Yue Fan
||
* Data collection
* Program processing
||
*Train dnf model with gun&nongun and test
||
*
|-

|-
|Jiawen Kang
||
* Adapting meta learning code to speaker recognition task.
||
* Running experiments.
||
*
|-

|-
|Ruiqi Liu
||
* Study meta-learning experiments and modify the code.
||
* Continue to study meta-learning experiments.
* Provide ASR training tools for Shengyuan company.
||
*
|-

|-
|Sitong Cheng
||
*
||
*
||
*
|-

|-
|Zhixin Liu
||
*
||
*
||
*
|-

|}

2020-03-23

2020-03-22T23:21:33Z

Liuruiqi：

{| class="wikitable"
!People !! This Week !! Next Week !! Task Tracking (DeadLine)
|-

|-
|Dong Wang
||
*
||
*
||
*
|-

|-
|Yunqi Cai
||
* Some experiments on EBMs model
* Modify the DNF patent
* Coding on VAE based bayes score model
||
* More experiments of VAE based bayes score model
||
*
|-

|-
|Zhiyuan Tang
||
*
||
*
||
*
|-

|-
|Lantian Li
||
*
||
*
||
*
|-

|-
|Ying Shi
||
*
||
*
||
*
|-

|-
|Wenqiang Du
||
*
||
*
||
*
|-

|-
|Haoran Sun
||
*
||
*
||
*
|-

|-
|Yue Fan
||
*
||
*
||
*
|-

|-
|Jiawen Kang
||
* Speaker vector distribution experiments.
* Arranging tf-kaldi codes.
||
* Runing meta learning experiments.
||
*
|-

|-
|Ruiqi Liu
||
* Arrang experiments code and observe the distribution of speakers in different scenes.

||
* Learn mate-learning and do experiments.
||
*
|-

|-
|Sitong Chengs
||
*
||
*
||
*
|-

|-
|Zhixin Liu
||
*
||
*
||
*
|-

|}

文件:8 speakers of interview and speech.png

2020-03-19T22:51:01Z

Liuruiqi：This picture is the distribution of 8 speakers (eight colors) in the two scenes of interview (1) and speech (2).

This picture is the distribution of 8 speakers (eight colors) in the two scenes of interview (1) and speech (2).

2020-03-16

2020-03-15T23:00:56Z

Liuruiqi：

{| class="wikitable"
!People !! This Week !! Next Week !! Task Tracking (DeadLine)
|-

|-
|Dong Wang
||
*
||
*
||
*
|-

|-
|Yunqi Cai
||
* investigate energy model
||
* investigate energy model on NL socre
||
*
|-

|-
|Zhiyuan Tang
||
*
||
*
||
*
|-

|-
|Lantian Li
||
*
||
*
||
*
|-

|-
|Ying Shi
||
*
||
*
||
*
|-

|-
|Wenqiang Du
||
*
||
*
||
*
|-

|-
|Haoran Sun
||
*
||
*
||
*
|-

|-
|Yue Fan
||
*Complete half of the data collection
*Promotion of crawler tools
||
*Simultaneously work on the data download and pipeline process of cn2
*Train dnf model with gun&nongun and test
||
*
|-

|-
|Jiawen Kang
||
*
||
*
||
*
|-

|-
|Ruiqi Liu
||
* Training model and arranging experiments data.
||
* Arranging experiments code.
* Investigate meta-learning and do experiments
||
*
|-

|-
|Sitong Cheng
||
*
||
*
||
*
|-

|-
|Zhixin Liu
||
*
||
*
||
*
|-

|-
|Haolin Chen
||
* Train double glow with white-noised TIMIT, mel sprctrogram
* Replace noisy model in double glow with VAE
* Full evaluation using PESQ, STOI, fwsegSNR on white-noised test data
||
* Summarize result
* Prepare paper
||
*
|-

|}

2020-03-09

2020-03-08T23:50:12Z

Liuruiqi：

{| class="wikitable"
!People !! This Week !! Next Week !! Task Tracking (DeadLine)
|-

|-
|Dong Wang
||
* Almost finished the simulation test for NL
* Completed proof of several important properties of NL
||
* Complete the draft of NL paper
* More investigation on subspace DNF
||
*
|-

|-
|Yunqi Cai
||
*
||
*
||
*
|-

|-
|Zhiyuan Tang
||
* Basic glow for speech normalization.
* Multi-conditioned glow, on phones first.
||
* Conditioned glow.
||
*
|-

|-
|Lantian Li
||
*
||
*
||
*
|-

|-
|Ying Shi
||
* Double AutoEncoder baseline
* compute fwSNR
||
* compare fwSNR between Double AutoEncoder Double Flow and DAE
* experiment about semi-supervise Double Flow
* verify the denoise result via ASR system
||
*
|-

|-
|Wenqiang Du
||
* Prepare materials for graduation
||
*
||
*
|-

|-
|Haoran Sun
||
*
||
*
||
*
|-

|-
|Yue Fan
||
*Optimize baseline model
*Supplement glow experiment
*Test the crawler code
||
*Do experiments on dnf
*Complete CN2‘s data download
||
*
|-

|-
|Jiawen Kang
||
* Investigation on adaptation.
* Arranging experiment results.
||
* Learning mate-learning.
||
*
|-

|-
|Ruiqi Liu
||
* More experiments for different speakers and scenes.
* Continue training the model.
||
* Learn Mate-learning，Domain adaptation.
||
*
|-

|-
|Sitong Cheng
||
*
||
*
||
*
|-

|-
|Zhixin Liu
||
*
||
*
||
*
|-

|}

2020-03-02

2020-03-01T23:11:12Z

Liuruiqi：

{| class="wikitable"
!People !! This Week !! Next Week !! Task Tracking (DeadLine)
|-

|-
|Dong Wang
||
*
||
*
||
*
|-

|-
|Yunqi Cai
||
* Finished patent
* Investigate the total covariance constrain of DNF and showed some results
* Preparing the weekly paper report
||
* More investigation on DNF
||
*
|-

|-
|Zhiyuan Tang
||
*
||
*
||
*
|-

|-
|Lantian Li
||
* Submit DNF patent.
* Complete DNF repository.
* Start frame-level DNF-SRE training.
||
* Go on DNF-SRE.
||
*
|-

|-
|Ying Shi
||
*
||
*
||
*
|-

|-
|Wenqiang Du
||
*Using the add noise、 spec-argument 、attention to improve model performance in different device channel
||
*
|-

|-
|Haoran Sun
||
*
||
*
||
*
|-

|-
|Yue Fan
||
*Build the baseline models
*Learn to use kaldi
||
*Optimize the baseline models
||
*
|-

|-
|Jiawen Kang
||
* Collect cnceleb speaker-birth map.
* Finish length, age and 11*11 geners experiments.
||
* Make some distribution figures for different speakers and geners.
* Design Cross-channel experiments.
||
*
|-

|-
|Ruiqi Liu
||
* Experiments on CN-Celeb different scenes and different length .
* Continue training the model.
||
* More experiments for different speakers and scenes.
||
*
|-

|-
|Sitong Cheng
||
*
||
*
||
*
|-

|-
|Zhixin Liu
||
*
||
*
||
*
|-

|-
|Haolin Chen
||
* Double WaveGlow on noisy TIMIT
* Test performance of Double Glow
* Optimize model structure
||
* Comprehensive evaluation on two models
||
*
|-

|}

2020-02-24

2020-02-23T23:14:08Z

Liuruiqi：

{| class="wikitable"
!People !! This Week !! Next Week !! Task Tracking (DeadLine)
|-

|-
|Dong Wang
||
*
||
*
||
*
|-

|-
|Yunqi Cai
||
* Writing the patent of DNF
* Test new code of DNF
* Investigate the total covariance constrain of DNF
||
* Finish the patent today
* Process the experiment data of total covariance constrain
||
*
|-

|-
|Zhiyuan Tang
||
*
||
*
||
*
|-

|-
|Lantian Li
||
*
||
*
||
*
|-

|-
|Ying Shi
||
*
||
*
||
*
|-

|-
|Wenqiang Du
||
*
||
*
||
*
|-

|-
|Haoran Sun
||
*
||
*
||
*
|-

|-
|Yue Fan
||
*
||
*
||
*
|-

|-
|Jiawen Kang
||
* Make scripts to calculate subset EER;
* Continiue model experiments;
* Paper introduction part.
||
* Length and age EER;
* Continiue model experiments;
||
*
|-

|-
|Ruiqi Liu
||
* Continue training the model.
* Experiments on CN-Celeb different scenes.
* Experiments on CN-Celeb different genders.
||
* Go on the task1.
* Experiments on CN-Celeb different length.
* Prepare paper writing.
||
*
|-

|-
|Sitong Cheng
||
*
||
*
||
*
|-

|-
|Zhixin Liu
||
*
||
*
||
*
|-

|-
|Haolin Chen
||
* Try Double Flow(Glow) with spectrogram as input, conditional/without condition.
||
* Evaluation.
* Optimize model structure.
||
*
|-

|}

2020-02-17

2020-02-17T00:11:09Z

Liuruiqi：

{| class="wikitable"
!People !! This Week !! Next Week !! Task Tracking (DeadLine)
|-

|-
|Dong Wang
||
* Code cleaning for DNF
* More review on DNF theory
* More review on speech enhancement with deep generative models
||
* More investigation on subspace DNF
* Draft paper for DNF properties
||
*
|-

|-
|Yunqi Cai
||
* retest the plda score(lenth norm false)
* train and test sota xvector
||
* more investigation on Between class var of DNF
||
*
|-

|-
|Zhiyuan Tang
||
*
||
*
||
*
|-

|-
|Lantian Li
||
* Update SOTA.
* Complete NF + LDA/PLDA.
||
* DNF + LDA/PLDA
||
*
|-

|-
|Ying Shi
||
* double flow denoise experiment and visualization
* DAE baseline
||
* DAE baseline
* timit ASR baseline
||
*
|-

|-
|Wenqiang Du
||
*
||
*
||
*
|-

|-
|Haoran Sun
||
*
||
*
||
*
|-

|-
|Yue Fan
||
*Arrange the work of the CN2
||
*baseline on svm&gmm
||
*
|-

|-
|Jiawen Kang
||
* Prepare SOTA vectors
* Prepare CNceleb as test set
* Continute experiments
||
* Continute experiments
* evaluatte models on diffierent geners
* Prepare paper writing
||
*
|-

|-
|Ruiqi Liu
||
* Experiments about ResNet and prepare vectors.

||
* Supplement the last experimental data and prepare paper writing.

||
*
|-

|-
|Sitong Cheng
||
* modify DNF code
||
* prepare paper writing
* step 2&3 with DNF
||
*
|-

|-
|Zhixin Liu
||
* Get initial conclusion of task 1
||
* Analyze results
* Prepare DNF
||
*
|-

|}

2020-02-10

2020-02-12T04:00:11Z

Liuruiqi：

{| class="wikitable"
!People !! This Week !! Next Week !! Task Tracking (DeadLine)
|-

|-
|Dong Wang
||
* Completed investigation of LDA for PLDA
* Completed TASLP draft
||
* Help submission of the TASLP paper
* More theoretical work on DNF
* More coding work on DNF repository
||
*
|-

|-
|Yunqi Cai
||
* prepare the experiment data of the paper. Make a plan of next experiment stage. Clear up the previous experiment data.
||
* Complete the sota SRE vector's test.
||
*
|-

|-
|Zhiyuan Tang
||
*
||
*
||
*
|-

|-
|Lantian Li
||
* Clear up research proposal
* Clear up code repository
* NF + LDA/PLDA
||
* NF + LDA/PLDA and DNF + GMM
||
*
|-

|-
|Ying Shi
||
* Finish research plan
* Read code about AlignFlow
||
* Finish experiment about double flow on spectrum and fbank
||
*
|-

|-
|Wenqiang Du
||
*
||
*
||
*
|-

|-
|Haoran Sun
||
* completed code modification
||
* perform experiments with lower dimensions
* perfect expriments with numeric results
||
*
|-

|-
|Yue Fan
||
*
||
*
||
*
|-

|-
|Jiawen Kang
||
* Experiments about ResNet model on Voxceleb;
* Read papers about robustness.
||
* Prepare SOTA vectors.
* Continute expriments.
||
*
|-

|-
|Ruiqi Liu
||
* Supplementing experimental data
||
* Experiments about ResNet and prepare vectors.
||
*
|-

|-
|Sitong Cheng
||
*
||
*
||
*
|-

|-
|Zhixin Liu
||
*
||
*
||
*
|-

|-
|Haolin Chen
||
* Read and modify code about Blow.
||
* Start running experiments.
||
*
|-

|}

2020-01-13

2020-01-13T23:49:56Z

Liuruiqi：

{| class="wikitable"
!People !! This Week !! Next Week !! Task Tracking (DeadLine)
|-

|-
|Dong Wang
||
*
||
*
||
*
|-

|-
|Yunqi Cai
||
*
||
*
||
*
|-

|-
|Zhiyuan Tang
||
*
||
*
||
*
|-

|-
|Lantian Li
||
*
||
*
||
*
|-

|-
|Ying Shi
||
*
||
*
||
*
|-

|-
|Wenqiang Du
||
* Write the first and second chapter of my thesis
* Baseline Model of Arabic ASR system(Data collection)
||
*
||
*
|-

|-
|Haoran Sun
||
*
||
*
||
*
|-

|-
|Yue Fan
||
*
||
*
||
*
|-

|-
|Jiawen Kang
||
*
||
*
||
*
|-

|-
|Ruiqi Liu
||
* Learn about resnet34 & Self Multi-Head Attention mechanism ,and do experiments on CN-celeb.
||
* AAM fine-tuning experiments.
* Finish the last experiments.

||
*
|-

|-
|Sitong Cheng
||
*
||
* Standard glow
||
*
|-

|-
|Zhixin Liu
||
*
||
*
||
*
|-

|}

2020 Spring Festival

2020-01-11T09:49:58Z

Liuruiqi：

{| class="wikitable"
!People !! Start time !! End time
|-

|-
|Dong Wang
||

||

|-

|-
|Yunqi Cai
||
2020.1.23
||
还未抢到票
|-

|-
|Zhiyuan Tang
||

||

|-

|-
|Lantian Li
||
2020.1.22
||
2020.2.1
|-

|-
|Ying Shi
||
2020.1.19
||
2020.1.29
|-

|-
|Wenqiang Du
||
2020.1.16
||
2020.2.02
|-

|-
|Haoran Sun
||
2020.1.19
||
2020.2.2
|-

|-
|Yue Fan
||
2020.1.16
||
2020.2.2
|-

|-
|Jiawen Kang
||
2020.1.19
||

|-

|-
|Ruiqi Liu
||
2020.1.18
||
2020.2.4
|-

|-
|Sitong Cheng
||
2020.1.21
||
2020.2.5 未抢票
|-

|-
|Zhixin Liu
||
2020.1.21
||
2020.2.5
|-

|}

2020-01-06

2020-01-06T00:07:57Z

Liuruiqi：

{| class="wikitable"
!People !! This Week !! Next Week !! Task Tracking (DeadLine)
|-

|-
|Dong Wang
||
*
||
*
||
*
|-

|-
|Yunqi Cai
||
*
||
*
||
*
|-

|-
|Zhiyuan Tang
||
*
||
*
||
*
|-

|-
|Lantian Li
||
*
||
*
||
*
|-

|-
|Ying Shi
||
*
||
*
||
*
|-

|-
|Wenqiang Du
||
* Data collection and collation. Updated to corpus1
* Write the first chapter of my thesis

||
* Continue to write your graduation thesis
||
*
|-

|-
|Haoran Sun
||
*
||
*
||
*
|-

|-
|Yue Fan
||
*
||
*
||
*
|-

|-
|Jiawen Kang
||
*
||
*
||
*
|-

|-
|Ruiqi Liu
||
* GhostVLAD pooling experiments .
* Solved the ASR problem for ShengYuanZhiNeng company.
||
* Continue the GhostVLAD pooling experiments .
* ResNet net experiments .
||
*
|-

|-
|Sitong Cheng
||
*
||
*
||
*
|-

|-
|Zhixin Liu
||
*
||
*
||
*
|-

|}

2020 Spring Festival

2020-01-02T00:21:47Z

Liuruiqi：

{| class="wikitable"
!People !! Start time !! End time
|-

|-
|Dong Wang
||

||

|-

|-
|Yunqi Cai
||

||

|-

|-
|Zhiyuan Tang
||

||

|-

|-
|Lantian Li
||
2020.1.22
||
2020.2.1
|-

|-
|Ying Shi
||
2020.1.19
||

|-

|-
|Wenqiang Du
||
2020.1.16
||

|-

|-
|Haoran Sun
||
2020.1.19
||
2020.2.2
|-

|-
|Yue Fan
||
2020.1.19
||

|-

|-
|Jiawen Kang
||
2020.1.19
||

|-

|-
|Ruiqi Liu
||
2020.1.19
||

|-

|-
|Sitong Cheng
||

||

|-

|-
|Zhixin Liu
||

||

|-

|}

2019-12-30

2019-12-30T00:51:07Z

Liuruiqi：

{| class="wikitable"
!People !! This Week !! Next Week !! Task Tracking (DeadLine)
|-

|-
|Dong Wang
||
* Investigate more on DNF, by designing the contrastive training. Seems does not work well. More constrained is requested to avoid divergence.
* Investigate the true contribution of DNF. It looks like between/within ratio has the best match with EER.
* Investigate DNF-based PLDA, not successful yet. The performance is not better than cosine.
||
* Keep on the investigation of DNF contribution.
* Complete the draft of DNF-based paper to TASLP.
||
*
|-

|-
|Yunqi Cai
||
* traning and test the DNF serials model on ivectors of SRE
||
*traning and test the DNF serials model on ivectors of LRE
||
*
|-

|-
|Zhiyuan Tang
||
* Denoising flow trained with only clean data.
||
* Denoising test.
||
*
|-

|-
|Lantian Li
||
* DNF-SRE (standard Kaldi IO)
* Clean up some tools (merge into Jungle)
||
* DNF-SRE
||
*
|-

|-
|Ying Shi
||
*
||
*
||
*
|-

|-
|Wenqiang Du
||
*
||
*
||
*
|-

|-
|Haoran Sun
||
*
||
*
||
*
|-

|-
|Yue Fan
||
*
||
*
||
*
|-

|-
|Jiawen Kang
||
*
||
*
||
*
|-

|-
|Ruiqi Liu
||
* Finished the self-attention pooling experiments with CN-Celeb and VoxCeleb.
||
* Finish the last experiments.
||
*
|-

|-
|Sitong Cheng
||
*
||
*
||
*
|-

|-
|Zhixin Liu
||
*
||
*
||
*
|-

|}

2019-12-23

2019-12-23T00:13:49Z

Liuruiqi：

{| class="wikitable"
!People !! This Week !! Next Week !! Task Tracking (DeadLine)
|-

|-
|Dong Wang
||
*
||
*
||
*
|-

|-
|Yunqi Cai
||
* Do experiment on NVP flow, try to reduce the within class var and enlarge the between class var
||
*
||
*
|-

|-
|Zhiyuan Tang
||
*
||
*
||
*
|-

|-
|Lantian Li
||
* Preparation on DNF SRE (complete baselines)
* Paper review
||
* DNF SRE
||
*
|-

|-
|Ying Shi
||
* Finish the patent
* subsapce denoise
||
* subspace denoise
||
*
|-

|-
|Wenqiang Du
||
*Review paper about mix bandwidth and bandwidth extension
*Do some experiments about mix bandwidth train and update in CVSS-740
||
*
||
*
|-

|-
|Haoran Sun
||
*
||
*
||
*
|-

|-
|Yue Fan
||
*
||
*
||
*
|-

|-
|Jiawen Kang
||
*
||
*
||
*
|-

|-
|Ruiqi Liu
||
*Experiments with CN-Celeb and VoxCeleb.
*Paper report.
||
*Continue to do experiments.
||
*
|-

|-
|Sitong Cheng
||
*
||
*
||
*
|-

|-
|Zhixin Liu
||
*
||
*
||
*
|-

|}

2019-12-16

2019-12-16T00:09:09Z

Liuruiqi：

{| class="wikitable"
!People !! This Week !! Next Week !! Task Tracking (DeadLine)
|-

|-
|Dong Wang
||
* Draft the DNF paper
* Investigate the difference between Fisher LDA and ML LDA.
* Design PNLDA model
||
* Complete and submit the DNF paper
* More investigation on VP and NVP based Gaussian information squeezing
||
*
|-

|-
|Yunqi Cai
||
* Test LDA-flow experiments on different dataset
||
*prepare the paper
||
*
|-

|-
|Zhiyuan Tang
||
*
||
*
||
*
|-

|-
|Lantian Li
||
*
||
*
||
*
|-

|-
|Ying Shi
||
*
||
*
||
*
|-

|-
|Wenqiang Du
||
* Experiment for my mentor's idear
||
* Review the paper about bandwidth extension in ICASSP2019 and Interspeech2019
||
*
|-

|-
|Haoran Sun
||
*
||
*
||
*
|-

|-
|Yue Fan
||
*
||
*
||
*
|-

|-
|Jiawen Kang
||
*Fix some code of tf-kaldi;
*Get the 3 experiments results, cvss will be updated soon when it is accessible;
*Attend the interview.
||
*Finish more experiments.
||
*
|-

|-
|Ruiqi Liu
||
*Three experiments with CN-Celeb and VoxCeleb.
||
*Continue to do experiments.
||
*
|-

|-
|Sitong Cheng
||
*
||
*
||
*
|-

|-
|Zhixin Liu
||
*
||
*
||
*
|-

|}

2019-12-09

2019-12-09T00:43:53Z

Liuruiqi：

{| class="wikitable"
!People !! This Week !! Next Week !! Task Tracking (DeadLine)
|-

|-
|Dong Wang
||
* MelGan and WaveGlow re-investigation. Good neural vocoder is done.
* Paper review on ICASSP 19, Interspeech 19.
||
* Investigate the performance degradation with pure VP-based x-vector regularization compared to the VP+linear model
* Design more concrete way of 'supervised flow', that involves supervision in sparse dimensions.
* Paper review on NIPS 19.
||
*
|-

|-
|Yunqi Cai
||
* VP-flow-lda Finished;
||
* 1 try VP-flow without the last layer maping matrix
* 2 control the class covariance matrix
* 3 explore the fitting limit of VP-flow
||
*
|-

|-
|Zhiyuan Tang
||
* WaveGlow model for audio augmentation.
||
* Test whether the aug helps ASR/VPR.
||
*
|-

|-
|Lantian Li
||
* Fix bugs in fnvpr, and release vpr product packages.
* Pull request egs of CN-Celeb.
* Study on flow models.
||
* Hire-Flow
||
*
|-

|-
|Ying Shi
||
* experiment about flow denoise
||
* finish the experiment and record it on cvss
* write patent
||
*
|-

|-
|Wenqiang Du
||
* Model parameter adjustment about my graduation thesis
||
* End2end in my graduation thesis
||
*
|-

|-
|Haoran Sun
||
*
||
*
||
*
|-

|-
|Yue Fan
||
* experiments on flow
||
* do the experiments and record it on cvss
||
*
|-

|-
|Jiawen Kang
||
* Sent materials to CUHK;
* Reading paper about model robustness;
* Kaldi egs checking.
||
* Experiences about CN-Celeb;
* Preparing for CUHK inverview.
||
*
|-

|-
|Ruiqi Liu
||
* Do experiments on CN-Celeb egs and VGG.
* tf-kaldi
||
* Experiments according to last week's plan
||
*
|-

|-
|Sitong Cheng
||
*
||
*
||
*
|-

|-
|Zhixin Liu
||
*
||
*
||
*
|-

|}

2019-12-09

2019-12-09T00:07:55Z

Liuruiqi：